© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42721
    Prev
    Next
    INDEX
    Explanations

    example or case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antie
    -0.07
    readonly
    -0.07
    ãģ¿ãģ¤
    -0.07
    澤
    -0.07
    å°Ĩæķ´ä¸ª
    -0.07
    æĪijä¸įæķ¢
    -0.07
    agnes
    -0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    çļĦä¸Ģå®ļ
    -0.07
    eram
    -0.07
    POSITIVE LOGITS
    为ä¾ĭ
    0.17
    çĤºä¾ĭ
    0.14
     example
    0.11
     ÙħØ«
    0.10
    ä¸Ģä¾ĭ
    0.09
    example
    0.09
    åIJ§
    0.09
    为代表
    0.09
     ejemplo
    0.09
    示ä¾ĭ
    0.08
    Activations Density 0.238%

    No Known Activations